A5061295513- Stock Market Forecasting Methods
- Forecasting Techniques and Applications
- Financial Markets and Investment Strategies
- Complex Systems and Time Series Analysis
- Energy Load and Power Forecasting
- Neural Networks and Applications
- Market Dynamics and Volatility
- Fuzzy Logic and Control Systems
- BIM and Construction Integration
- Evolutionary Algorithms and Applications
- Smart Grid Energy Management
- Financial Risk and Volatility Modeling
- Electric Power System Optimization
- Neural dynamics and brain function
- Manufacturing Process and Optimization
- Time Series Analysis and Forecasting
- Advanced Data Processing Techniques
- Rough Sets and Fuzzy Logic
- Capital Investment and Risk Analysis
- Stochastic processes and financial applications
- Visual perception and processing mechanisms
- CCD and CMOS Imaging Sensors
- Fiscal Policies and Political Economy
- Advanced Manufacturing and Logistics Optimization
- Fiscal Policy and Economic Growth
Missouri University of Science and Technology
2013-2024
University of Missouri
2007-2020
University of Tulsa
2008-2011
Engineering Systems (United States)
1997-2003
Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields, including stock market investment. However, few studies have focused on forecasting daily returns, especially when using powerful techniques, such as deep neural networks (DNNs), to perform the analyses. DNNs employ based combination of network structure, activation function, and model parameters, their performance depending format representation....
Multivariate time series classification has been broadly applied in diverse domains over the past few decades. However, before applying algorithms, vast majority of current studies extract hand-engineered features that are assumed to detect local patterns series. Therefore, efficiency and precision these approaches heavily dependent on quality variables defined by domain experts. Recent improvements deep learning offer opportunities avoid such an intensive hand-crafted feature engineering...
Choosing the appropriate forecasting technique to employ is a challenging issue and requires comprehensive analysis of empirical results. Recent research findings reveal that performance evaluation models depends on accuracy measures adopted. Some methods indicate superior when error based metrics are used, while others perform better precision values adopted as measures. As scholars tend use smaller subset assess models, there need for concept multiple dimensions assure robustness...
Stock market forecasting research offers many challenges and opportunities, with the of individual stocks or indexes focusing on either level (value) future prices, direction price movement. A three-stage stock prediction system is introduced in this article. In first phase, Multiple Regression Analysis applied to define economic financial variables which have a strong relationship output. second Differential Evolution-based type-2 Fuzzy Clustering implemented create model. For third Neural...
Volatility forecasting in the financial markets, along with development of models, is important areas risk management and asset pricing, among others. Previous testing has shown that asymmetric GARCH models outperform other family regard to volatility prediction. Utilizing this information, three popular Neural Network (Feed-Forward Back Propagation, Generalized Regression, Radial Basis Function) are implemented help improve performance GJR(1,1) method for estimating over next forty-four...
Complex Event Processing (CEP) is a novel and promising methodology that enables the real-time analysis of stream event data. The main purpose CEP detection complex patterns from atomic semantically low-level events such as sensor, log, or RFID Determination rule for matching these simple based on temporal, semantic, spatial correlations central task systems. In current design systems, experts provide patterns. Having reached maturity, Big Data Systems Internet Things (IoT) technology...
This paper discusses a hybrid prediction model that combines differential evolution-based fuzzy clustering with inference neural network for performing an index level forecast. In the first phase of proposed model, stepwise regression analysis is implemented to determine combination inputs have strongest forecasting ability. Next, selected variables are grouped by means method, allowing extraction rules be determined. For final stage, predict market prices using from previous stage.
The dynamic planning for a system-of-systems is challenging endeavor. Department of Defense (DoD) programs constantly face challenges to incorporate new systems and upgrade existing over period time under threats, constrained budget, uncertainty. It therefore necessary the DoD be able look at future scenarios critically assess impact technology stakeholder changes. currently looking options that signify affordable acquisition selections lessen cycle early addition. This paper gives an...
Abstract This paper applies deep learning models to predict Bitcoin price directions and the subsequent profitability of trading strategies based on these predictions. The study compares performance convolutional neural network–long short-term memory (CNN–LSTM), long- time-series network, temporal ARIMA (benchmark) for predicting prices using on-chain data. Feature-selection methods—i.e., Boruta, genetic algorithm, light gradient boosting machine—are applied address curse dimensionality that...
Destruction from natural and man-made disasters can result in extensive damage to the affected area's infrastructure. While destruction results costs that are necessary restore physical repair of existing infrastructure, a wider economic impact is often indirectly measured felt. Policy-makers generally focus only on losses directly caused by destruction, such as replacement roads bridges, yet tend overlook consequences indirect losses. This study proposes framework estimate loss due damaged...
An approach to estimate the indirect economic loss due damaged bridges within highway system from an earthquake event is presented. The cost considered refers increased transportation only. study zone covers St. Louis metropolitan area and its surrounding suburban regions. scenario centered in Louis, with a magnitude 7.0 used. direct was primarily damage bridges, which causes increase travel time distance network. This information then used as input for model. examined perspective. results...
There are fundamental difficulties when only using a supervised learning philosophy to predict financial stock short-term movements. We present reinforcement-oriented forecasting framework in which the solution is converted from typical error-based approach goal-directed match-based method. The real market timing ability addressed as well traditional goodness-of-fit-based criteria. develop two applicable hybrid prediction systems by adopting actor-only and actor-critic reinforcement...